This paper introduces a novel approach to texture synthesis based on generative adversarial networks (GAN) (Goodfellow et al., 2014). We extend the structure of the input noise distribution by constructing tensors with different types of dimensions. We call this technique Periodic Spatial GAN (PSGAN). The PSGAN has several novel abilities which surpass the current state of the art in texture synthesis. First, we can learn multiple textures from datasets of one or more complex large images. Second, we show that the image generation with PSGANs has properties of a texture manifold: we can smoothly interpolate between samples in the structured noise space and generate novel samples, which lie perceptually between the textures of the original dataset. In addition, we can also accurately learn periodical textures. We make multiple experiments which show that PSGANs can flexibly handle diverse texture and image data sources. Our method is highly scalable and it can generate output images of arbitrary large size.

本文提出了一种基于生成对抗网络（GAN）的纹理合成新方法，称为周期空间GAN（PSGAN），该方法可以从复杂大型图像数据集中学习多种纹理，生成的样本在结构化噪声空间内可以平滑插值，生成新样本，并可以准确学习周期性纹理，能够灵活处理不同的纹理和图像数据源，可扩展性强，能够生成任意大小的输出图像。

使用周期空间 GAN 学习纹理流形